Set the working directory:

  1. Download “StudentSurvey.csv” to your computer.
  2. Set Working directory to the folder you saved your file in.
  3. read the file using read.csv command.
#If your assignment does not render, you might need to install.packages("htmltools")

Instructions:

Read the StudentSurvey into this markdown and answers the following questions

#read the StudentSurvey.csv in here
StudentSurvey <- read.csv("StudentSurvey.csv", stringsAsFactors = FALSE)

Check the data structure:

#check the head of the data set
head(StudentSurvey)
##        Year Sex Smoke   Award HigherSAT Exercise TV Height Weight Siblings
## 1    Senior   M    No Olympic      Math       10  1     71    180        4
## 2 Sophomore   F   Yes Academy      Math        4  7     66    120        2
## 3 FirstYear   M    No   Nobel      Math       14  5     72    208        2
## 4    Junior   M    No   Nobel      Math        3  1     63    110        1
## 5 Sophomore   F    No   Nobel    Verbal        3  3     65    150        1
## 6 Sophomore   F    No   Nobel    Verbal        5  4     65    114        2
##   BirthOrder VerbalSAT MathSAT  SAT  GPA Pulse Piercings
## 1          4       540     670 1210 3.13    54         0
## 2          2       520     630 1150 2.50    66         3
## 3          1       550     560 1110 2.55   130         0
## 4          1       490     630 1120 3.10    78         0
## 5          1       720     450 1170 2.70    40         6
## 6          2       600     550 1150 3.20    80         4
#check the dimensions
dim(StudentSurvey)
## [1] 79 17
#create a table of students'sex and "HigherSAT"
table(StudentSurvey$Sex, StudentSurvey$HigherSAT)
##    
##     Math Verbal
##   F   25     15
##   M   24     15
# Display summary statistics for VerbalSAT
summary(StudentSurvey$VerbalSAT)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   420.0   550.0   580.0   583.2   630.0   720.0
#Find the average GPA of students
mean(StudentSurvey$GPA, na.rm = TRUE)
## [1] 3.169114
#Create a new dataframe, call it "column_df". This new dataframe should contain students' weight and number of hours the exercise column_df <- data.frame(
  column_df <- data.frame(
    Weight = StudentSurvey$Weight,
    ExerciseHours = StudentSurvey $Exercise
  )

# Print it out
column_df
##    Weight ExerciseHours
## 1     180            10
## 2     120             4
## 3     208            14
## 4     110             3
## 5     150             3
## 6     114             5
## 7     128            10
## 8     235            13
## 9     115            12
## 10    140            12
## 11    135             6
## 12    110            10
## 13     99             3
## 14    165             7
## 15    120             2
## 16    154            14
## 17    110            10
## 18    145            14
## 19    195            20
## 20    200             7
## 21    167            12
## 22    175            10
## 23    155             6
## 24    185            14
## 25    190            12
## 26    165            10
## 27    175             8
## 28    126             0
## 29    187            10
## 30    170             6
## 31    158             5
## 32    119            24
## 33    205             2
## 34    129            10
## 35    145             6
## 36    130             5
## 37    215             5
## 38    135            12
## 39    145             2
## 40     98             7
## 41    150            15
## 42    159             5
## 43    174             7
## 44    160            15
## 45    165             8
## 46    161            14
## 47    130             4
## 48    175            15
## 49    255             4
## 50    160            15
## 51    160             3
## 52     95             3
## 53    115            15
## 54    120            20
## 55    135             3
## 56    180             6
## 57    155            12
## 58    110             4
## 59    215            20
## 60    140            10
## 61    195            10
## 62    185             4
## 63    185             9
## 64    209            12
## 65    145             2
## 66    180             2
## 67    170             5
## 68    135             5
## 69    165             6
## 70    137            10
## 71    147             4
## 72    150             5
## 73    155            17
## 74    160             7
## 75    130             2
## 76    180             8
## 77    150             1
## 78    205            14
## 79    115            12
#Access the fourth element in the first column from the StudentSurvey's dataset.
StudentSurvey[4, 1]
## [1] "Junior"